npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@kanesong/wj

v0.1.4

Published

WenJing Agent-Native CLI — 文镜平台内容生成命令行工具,支持视频、图片、音频和文本生成

Downloads

360

Readme

wj — WenJing CLI

文镜平台内容生成命令行工具,面向 Codex、Claude Code、Cursor、OpenClaw 等 AI Agent 使用。

当前公共包只包含内容生成相关能力:视频、图片、图片编辑、音频、文本,以及登录、任务查询、参数 schema 和 skills 安装。

安装

npm install -g @kanesong/wj
# 或临时使用
npx @kanesong/wj --version

快速开始

# 登录
wj login --username 13800138000

# 查看当前用户和算力余额
wj whoami

# 生成视频并等待完成
wj video.create --model kling-omni --prompt "一只猫咪在草地上奔跑" --wait

# 查询视频任务
wj video.query --id <taskId> --poll

# 生成图片
wj image.create --model gpt-image-2 --prompt "一只穿着宇航服的猫在月球上" --ratio 9:16 --resolution 2K --wait

# 图片编辑
wj image.edit --type inpaint --image-url <url> --prompt "把背景换成月球表面" --wait

# 文本推理
wj text.request --model gpt-5 --prompt "写一段产品介绍"

# 查看命令参数
wj schema video.create --model kling-omni
wj schema

命令体系

| 类型 | 示例 | 适合 | |---|---|---| | 快捷命令 | wj generate video --model kling-omni | 人类 + AI Agent | | 资源命令 | wj video.create --model kling-omni | AI Agent | | 参数说明 | wj schema image.create --model gpt-image-2 | 查询可用参数 |

可用能力

| 能力 | 主要命令 | |---|---| | 视频生成 | video.create, video.query, generate video | | 图片生成 | image.create, image.query, generate image | | 图片编辑 | image.edit | | 音频生成 | audio.create, audio.query, audio.voices, audio.voice-clone | | 文本推理 | text.request, text.stream, text.conversation | | 账户 | login, logout, whoami | | 工具 | schema, skills add |

公共包不包含 CRM、组织管理、支付账单、素材授权商城、部署命令或 raw API 逃生舱。

模型与参数

使用 wj schema 查看完整命令列表,使用 --model--type 查看某个模型的参数:

wj schema video.create --model kling-omni
wj schema image.create --model gpt-image-2
wj schema image.edit --model inpaint
wj schema audio.create --model minimax-tts
wj schema text.request --model gpt-5

安装 AI Agent Skills

# 安装到当前项目(自动检测已安装的 Agent)
wj skills add

# 安装到全局
wj skills add --global

# 安装到所有支持的本地 Agent 目录
wj skills add --all --yes

# 跳过确认
wj skills add --global --yes

支持: Codex (~/.codex/skills/)、Claude Code (~/.claude/skills/)、Cursor (~/.cursor/skills/)、OpenClaw (~/.openclaw/skills/)

随包 skills 只包含内容生成相关说明:wj-sharedwj-videowj-imagewj-image-editwj-audiowj-text

环境变量

| 变量 | 说明 | 默认值 | |---|---|---| | WJ_PORTAL_URL | Portal 内容生成服务地址 | https://api.wenjing.art | | WJ_USERNAME | 默认账号(可替代 --username) | — | | WJ_PASSWORD | 默认密码(可替代 --password) | — |

本地开发时显式覆盖地址:

WJ_PORTAL_URL=http://localhost:8088 wj whoami

安全说明

  • JWT token 存储在 OS keychain,AI Agent 无法通过 CLI 输出读取原始 token。
  • 所有命令默认输出 JSON,便于 Agent 稳定解析。
  • 调用记录写入 ~/.wenjing/audit.log

开发

git clone ...
cd wenjing-cli
npm install
npm run dev -- --help
npm run build